FIDES-Live: 评估顺序交易智能体的行为一致性
FIDES-Live: Evaluating Behavioral Concordance in Sequential Trading Agents
Arther Tian · Alex Ding · Simon Wu · Aaron Chan
中文摘要
顺序交易智能体生成的决策、订单、执行回执、账户状态及报告往往不一致，即使最终组合价值计算正确。FIDES-Live 将 FIDES 从生成策略一致性扩展至顺序智能体轨迹审计。该协议分离结构化决策有效性、可选数值承诺遵循、执行与账本对账及基于回执的报告，并明确覆盖范围与不可评分结果。研究回溯审计了 7,299 个加密货币账户轮次及 310 轮股票试点中的 10 条推理路径，使用真实市场观察与本地模拟执行。加密货币决策有效率为 97.35%，可评分响应中结构化报告准确率为 90.81%，但路径级性能差异显著。整体承诺遵循率为 94.36%，非空订单提案中降至 62.63%，有效空提案为 97.56%。所有保留现金与持仓变动均与成交记录对账一致。短窗口标记收益仅提供描述性背景，未验证一致性是否预测超额收益。这些观察建议分开报告一致性、证据覆盖、活动及财务结果，但未确立长期交易技能、解释语义忠实性或审计反馈的因果效益。
关键要点
- 01提出 FIDES-Live 协议，将审计范围从策略一致性扩展至顺序智能体轨迹，分离决策、执行与报告维度。
- 02在 7,299 个加密货币账户轮次中，决策有效率为 97.35%，结构化报告准确率为 90.81%。
- 03非空订单提案的承诺遵循率仅 62.63%，显著低于有效空提案的 97.56%，揭示执行约束下的性能差异。
- 04所有现金与持仓变动均与成交记录对账一致，执行控制与不可用报价解释了独立的拒绝群体。
- 05研究未确立长期交易技能或解释的语义忠实性，短窗口收益仅作为描述性背景而非一致性预测测试。
解读
尚无解读。
原始英文摘要
arXiv:2610.36476v1 Announce Type: cross Abstract: Sequential trading agents produce decisions, orders, execution receipts, account states, and reports that need not agree, even when the final portfolio value is correctly computed. We present FIDES-Live, an operational extension of FIDES from generated strategy concordance to the audit of sequential agent traces. The protocol separates structured decision validity, optional numerical commitment adherence, execution and ledger reconciliation, and receipt- grounded reporting, with explicit coverage and unscorable outcomes. We retrospectively audit ten requested inference routes over 7,299 cryptocurrency account-rounds and a 310-round equity pilot, using real market observations and local paper execution. Cryptocurrency decision validity is 97.35% and structured reporting accuracy is 90.81% among scorable responses, but route-level decision and reporting performance can diverge sharply. Commitment adherence is 94.36% overall; it falls to 62.63% on constraints emitted with nonempty order proposals, compared with 97.56% for valid empty proposals. All retained cash and position transitions reconcile with recorded fills, while execution controls and unavailable quotes explain separate rejection populations. Short-window marked returns provide descriptive context rather than a new test of whether concordance predicts alpha. These observations motivate reporting concordance, evidence coverage, activity, and financial outcomes separately. They do not establish long-run trading skill, semantic faithfulness of explanations, or causal benefits from audit feedback.